Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

7.6%15.2%22.9%30.5% · Jun 202019922001200920172026
48 results for quantization-aware training

Quantization-aware training can recover accuracy lost by post-training quantization.

problem Post-training quantization (PTQ) can fail sharply at aggressive bitwidths.
method A unified geometric framework that explains PTQ failure and QAT recovery.
result QAT has a useful bias that steers iterates back into the basin.

APQ jointly optimizes neural architecture, pruning, and quantization for efficient inference.

problem Efficient deep learning inference on resource-constrained hardware.
method Joint optimization of neural architecture, pruning, and quantization policy using a quantization-aware accuracy predictor.
result Joint optimization leads to 2.3% higher ImageNet accuracy with reduced latency and energy consumption.

FrostNet improves INT8 quantization efficiency in mobile networks.

problem The importance of network architecture for optimal INT8 quantization.
method Quantization-aware training (QAT) with StatAssist and GradBoost, hardware-aware NAS.
result FrostNets achieve higher recognition accuracy with comparable latency when quantized.

This study improves Ernie's accuracy for INT8 inference by modifying its training process.

problem Improving the accuracy of pre-trained models like Ernie for low precision inference.
method Integrates a regularizer into the training process to make it more robust to quantization.
result Increased INT8 accuracy for Ernie models.

We extend quantization-aware training to extreme model compression.

problem Maximizing model accuracy with minimal model size.
method Quantize a random subset of weights during training, allowing unbiased gradients through other weights.
result Established new state-of-the-art compromises between accuracy and model size.

We analyze the effect of quantizing weights and activations of neural networks on their loss and derive a simple regularization scheme that improves robustness against post-training quantization. By training quantization-ready networks, our approach enables storing a single set of weights that can be quantized on-deman…

2020-02-18abs ↗pdf ↗

Study finds optimal learning rate schedules for sub-100M quantization-aware training across bit-widths.

problem Optimal learning rate schedules for quantization-aware training depend on bit-width.
method Factorial grid testing over bit-width, warmdown fraction, LR magnitude, model size, and seed.
result INT6 QAT requires a different schedule than higher-precision training, falsifying the primary hypothesis.

There is a mismatch between the standard theoretical analyses of statistical machine learning and how learning is used in practice. The foundational assumption supporting the theory is that we can represent features and models using real-valued parameters. In practice, however, we do not use real numbers at any point d…

2019-05-27abs ↗pdf ↗

Unified finetuning of all quantization degrees of freedom achieves state-of-the-art 4-bit quantization.

problem Achieving high accuracy in quantized neural networks while maintaining speed and resource constraints.
method Quantization-aware finetuning (QFT) that jointly optimizes all quantization degrees of freedom.
result 4-bit weight quantization results on-par with state-of-the-art (SoTA) within PTQ constraints.

StatQAT optimizes quantization for deep networks, reducing computational cost and memory usage.

problem Optimal quantization parameters selection for deep neural networks with diverse data distributions.
method Statistical error analysis framework for uniform and floating-point quantization, iterative and analytic quantizers designed for arbitrary and Gaussian-like distributions.
result Improved accuracy and stability in training low-precision neural networks.

Paper develops a statistical framework for quantized training of deep neural networks.

problem Lack of theoretical understanding of gradient quantization in FQT.
method Presented a statistical framework for analyzing FQT algorithms, viewing quantized gradient as a stochastic estimator of QAT gradient.
result Developed two novel gradient quantizers with smaller variance than existing per-tensor quantizer.

Real-time semantic segmentation for autonomous vehicles on FPGA reduces latency and power consumption.

problem Efficient real-time semantic segmentation for autonomous vehicles.
method Compressed ENet architecture, FPGA deployment, batch processing, filter reduction, quantization-aware training.
result Reduced latency to 3 ms per image with batch size of ten and 40% resource utilization.

Two methods reduce BN and DNN complexity, balancing size and accuracy.

problem Balancing model size and prediction accuracy in Bayesian networks and deep neural networks.
method Quantization-aware training and tree-augmented naive Bayes structure learning extension.
result Pareto optimal models found for small-scale scenarios.

Low-precision representation of deep neural networks (DNNs) is critical for efficient deployment of deep learning application on embedded platforms, however, converting the network to low precision degrades its performance. Crucially, networks that are designed for embedded applications usually suffer from increased de…

2019-06-07abs ↗pdf ↗

BiTAT improves neural network quantization for edge devices by focusing on weight dependencies and disentangling them.

problem Performance degradation of compact neural networks under extreme quantization.
method Task-dependent Aggregated Transformation (BiTAT) method that orthonormalizes weights and progressively quantizes them.
result BiTAT effectively preserves model performance on ImageNet and CIFAR-100 with compact backbones.

We address the problem of phase retrieval (PR) from quantized measurements. The goal is to reconstruct a signal from quadratic measurements encoded with a finite precision, which is indeed the case in many practical applications. We develop a rank-1 projection algorithm that recovers the signal subject to ensuring cons…

2018-10-02abs ↗pdf ↗

Taylorized training improves neural network training at finite width.

problem Understanding and improving neural network training at finite width.
method Training the k-th order Taylor expansion of the neural network at initialization.
result Taylorized training agrees with full neural network training better as k increases and can significantly close the performance gap.

Self-training outperforms pre-training on COCO object detection and segmentation datasets.

problem The effectiveness of pre-training in improving object detection and segmentation models is limited.
method Investigated self-training as an alternative method to utilize additional data.
result Self-training consistently improves model performance across various dataset sizes and data augmentation levels.

New method reveals how training data influence diffusion model outputs.

problem Difficulty in assessing training data impact on diffusion model outputs.
method Use of ensembles trained on carefully engineered splits of training data to identify influential training examples.
result Demonstrated the viability of ensembles as generative models and validity of assessing influence.

New MIP methods improve training of integer-valued neural networks.

problem Training integer-valued neural networks with limited data and resources.
method Formulated new MIP models to optimize training efficiency and handle more data.
result Significantly outperforms previous state-of-the-art methods in accuracy, training time, and data usage.

Making neural networks robust against adversarial inputs has resulted in an arms race between new defenses and attacks. The most promising defenses, adversarially robust training and verifiably robust training, have limitations that restrict their practical applications. The adversarially robust training only makes the…

2018-11-06abs ↗pdf ↗

Paper explores fast adversarial training to improve robustness with less computation.

problem Efficiently defending against adversarial examples.
method Integrates simple self-attacks for faster training, focusing on overfitting recovery.
result Shows superior robust accuracy with reduced training time compared to strong adversarial training.

Stochastic gradient decent~(SGD) and its variants, including some accelerated variants, have become popular for training in machine learning. However, in all existing SGD and its variants, the sample size in each iteration~(epoch) of training is the same as the size of the full training set. In this paper, we propose a…

2019-06-11abs ↗pdf ↗

Crowdsourced training of large neural networks with decentralized Mixture-of-Experts.

problem Expensive training of large neural networks limits research contributions.
method Learning@home: decentralized Mixture-of-Experts for large, poorly connected participants.
result Performance and reliability of Learning@home surpass conventional distributed training.

Pre-training is crucial for learning deep neural networks. Most of existing pre-training methods train simple models (e.g., restricted Boltzmann machines) and then stack them layer by layer to form the deep structure. This layer-wise pre-training has found strong theoretical foundation and broad empirical support. Howe…

2015-06-07abs ↗pdf ↗

New method reconstructs significant parts of training data from neural networks.

problem Understanding and reconstructing training data from neural networks.
method Proposes a novel reconstruction scheme based on recent theoretical results about neural network training.
result Shows that a significant fraction of training data can be reconstructed from neural network parameters.

The paper studies the asymptotic behavior of adversarial training under \ell_\infty-perturbation.

problem Theoretical guarantees for sparsity-recovery in adversarial training.
method Investigation of the asymptotic distribution of the adversarial training estimator in generalized linear models.
result The asymptotic distribution of the adversarial training estimator under \ell_\infty-perturbation could have a positive probability mass at 0 when the true parameter is 0.

This paper introduces 'General Cyclical Training' for neural networks.

problem Improving training efficiency and performance of neural networks.
method Cyclical training phases with varying hyperparameters, batch sizes, loss functions, and data augmentation.
result Cyclical weight decay, softmax temperature, and gradient clipping enhance model accuracy.

Theoretical study shows adversarial training improves robustness in deep learning models.

problem Ensuring robustness in pre-trained deep learning models.
method Theoretical analysis of adversarial training and feature purification in two-layer neural networks.
result Adversarial training leads to feature purification, making models more robust to attacks.

Joint training improves model accuracy by selectively using privileged information.

problem Two-stage training can lead to model failure with noisy privileged information.
method Joint training of two models to use privileged information selectively.
result Joint training outperforms two-stage baselines on synthetic and real-world tasks.

ShadowSync separates background synchronization for scalable distributed training.

problem Reducing synchronization overhead in distributed training for high scalability.
method Separates synchronization from training and runs it in the background.
result Achieves both high throughput and excellent model quality at scale.

The study finds a theoretical bound for pre-training iterations needed for pruning to yield good subnetwork performance.

problem Discovering efficient subnetworks within pre-trained dense networks.
method Mathematical analysis of a two-layer, fully-connected network, validating with a multi-layer perceptron trained on MNIST.
result A logarithmically dependent threshold on dataset size for successful pruning.

Adversarial training, in which a network is trained on adversarial examples, is one of the few defenses against adversarial attacks that withstands strong attacks. Unfortunately, the high cost of generating strong adversarial examples makes standard adversarial training impractical on large-scale problems like ImageNet…

2019-04-29abs ↗pdf ↗